Towards Tool Use Alignment of Large Language Models
Abstract: Recently, tool use with LLMs has become one of the primary research topics as it can help LLM generate truthful and helpful responses.
Existing studies on tool use with LLMs primarily focus on enhancing the tool-calling ability of LLMs. In practice, like chat assistants, LLMs are also required to align with human values in the context of tool use. Specifically, LLMs should refuse to answer unsafe tool use relevant instructions and insecure tool responses to ensure their reliability and harmlessness. At the same time, LLMs should demonstrate autonomy in tool use to reduce the costs associated with tool calling. To tackle this issue, we first introduce the principle that LLMs should follow in tool use scenarios: H2A. The goal of H2A is to align LLMs with $\textbf{helpfulness}$, $\textbf{harmlessness}$, and $\textbf{autonomy}$. In addition, we propose ToolAlign, a dataset comprising instruction-tuning data and preference data to align LLMs with the H2A principle for tool use. Based on ToolAlign, we develop LLMs by supervised fine-tuning and preference learning, and experimental results demonstrate that the LLMs exhibit remarkable tool-calling capabilities, while also refusing to engage with harmful content, and displaying a high degree of autonomy in tool utilization. The code and datasets are avaliable at: https://anonymous.4open.science/r/ToolAlign.
Paper Type: Long
Research Area: Language Modeling
Research Area Keywords: security and privacy, fine-tuning
Contribution Types: NLP engineering experiment, Data resources
Languages Studied: English
Submission Number: 4541
Loading